78trust / 100

Agentglass

by agentglass.net in Other

MCP serverPassing, checked 8 h ago

Scan any public URL for hidden instructions aimed at AI agents (prompt injection). Free, no auth.

https://agentglass.net/mcp
Tools
1
open to any client
Uptime
100%
last 30 days
Response time
455 ms
549 ms slowest 5%
Last check
Passed
8 h ago, next any minute now

Scan it nowHow to connect

Reliability

All checks passedSome failedAll failedNot checked

Status and outage history · Atom feed · Watch with other listings

How to connect

Add it to any MCP client that supports remote servers.

{
  "mcpServers": {
    "agentglass": {
      "type": "http",
      "url": "https://agentglass.net/mcp"
    }
  }
}

1 tools

  • scan_job_page

    Scan a public URL, typically a job posting or application page, for hidden text, HTML comments, metadata and script content that try to instruct an AI agent (prompt injection). Returns a risk level (clean, notice, suspicious, high), a short verdict and the evidence, so the agent…

Security scan

No findings

We scan names, descriptions and tool definitions for hidden instructions and other prompt-injection patterns.

Recent checks

WhenResultHTTPTime
8 h agoPassed200444 ms
17 h agoPassed200446 ms
27 h agoPassed200467 ms
36 h agoPassed200479 ms
46 h agoPassed200480 ms
Show 10 older checks
2 days agoPassed200470 ms
3 days agoPassed200434 ms
3 days agoPassed200479 ms
3 days agoPassed200444 ms
4 days agoPassed200477 ms
4 days agoPassed200453 ms
5 days agoPassed200399 ms
5 days agoPassed200416 ms
6 days agoPassed200464 ms
6 days agoPassed200595 ms